Power System Resilience Enhancement Using Intelligent Monitoring and Control Techniques: A State-of-the-Art Review

Abstract

Power system resilience has emerged as a critical priority in modern electrical grids, driven by increasing frequency of extreme weather events, cyber threats, and the integration of distributed energy resources. This comprehensive review examines state-of-the-art intelligent monitoring and control techniques designed to enhance power system resilience across pre-event, during-event, and post-event phases. The paper systematically analyzes advanced monitoring technologies including phasor measurement units, SCADA systems, IoT sensors, and smart metering infrastructure, alongside intelligent control paradigms encompassing artificial intelligence, machine learning, adaptive control, model predictive control, and distributed multi-agent systems. Through critical evaluation of recent implementations and case studies, this review identifies key integration approaches, performance metrics, and validation methodologies. Significant findings include the achievement of 95.57% cyber-attack detection accuracy using time-frequency convolutional neural networks, reduction of disaster recovery computational time from 2.6 hours to 7.3 seconds through AI-assisted optimization, and 50% reduction in required photovoltaic-battery system capacity through intelligent model predictive control. The review also addresses persistent challenges including cybersecurity vulnerabilities, data integrity concerns, scalability limitations, and the need for physics-informed hybrid approaches. Future research directions emphasize the integration of physical constraints with machine learning, adversarial-robust learning frameworks, and edge-cloud co-design for distributed resilience. This synthesis provides researchers and practitioners with a comprehensive understanding of current capabilities and future pathways for resilience-oriented power system design.